Csi prediction method and apparatus, communication device, and readable storage medium

Abstract

This application discloses a CSI prediction method and apparatus, a communication device, and a readable storage medium. The method includes: in a case that a terminal meets a triggering condition for CSI prediction and the terminal receives first information, performing by the terminal, CSI prediction to obtain predicted CSI content, where the first information is used to indicate the terminal to perform CSI prediction.

What is claimed is: 
     
         1 . A channel state information (CSI) prediction method, comprising:
 in a case that a terminal meets a triggering condition for CSI prediction and the terminal receives first information, performing, by the terminal, CSI prediction to obtain predicted CSI content, wherein the first information is used to indicate the terminal to perform CSI prediction.   
     
     
         2 . The method according to  claim 1 , wherein the performing, by the terminal, CSI prediction to obtain predicted CSI content comprises:
 activating, by the terminal, a CSI prediction model according to the first information, and performing CSI prediction through the activated CSI prediction model to obtain the predicted CSI content; wherein   input information of the CSI prediction model comprises CSI acquired from a historical measurement on a CSI-RS resource obtained by the terminal.   
     
     
         3 . The method according to  claim 2 , wherein the activating, by the terminal, a CSI prediction model according to the first information, and performing CSI prediction through the activated CSI prediction model to obtain the predicted CSI content comprises:
 obtaining, by the terminal, a to-be-activated CSI prediction model and a sample threshold for the CSI prediction model according to the first information;   activating, by the terminal, a corresponding CSI prediction model; and   in a case that an amount of CSI measurement data of the terminal is greater than or equal to the sample threshold for the CSI prediction model, performing, by the terminal, CSI prediction through the activated CSI prediction model to obtain the predicted CSI content;   or,   obtaining, by the terminal, a to-be-activated CSI prediction model according to the first information;   activating, by the terminal, a corresponding CSI prediction model; and   in a case that an amount of CSI measurement data of the terminal is greater than or equal to the sample threshold for the CSI prediction model, performing, by the terminal, CSI prediction through the activated CSI prediction model to obtain the predicted CSI content.   
     
     
         4 . The method according to  claim 3 , wherein the to-be-activated CSI prediction model is a CSI prediction model corresponding to location information of the terminal, or the to-be-activated CSI prediction model is a CSI prediction model corresponding to a channel characteristic measured. 
     
     
         5 . The method according to  claim 1 , wherein before the receiving first information, the method further comprises:
 sending, by the terminal, second information through a first resource, wherein the second information is used to indicate that the terminal meets the triggering condition of CSI prediction; wherein   the first information is sent by the network-side device in a case that energy on the first resource is detected to be greater than or equal to a first threshold.   
     
     
         6 . The method according to  claim 1 , wherein the triggering condition for CSI prediction comprises one or more of the following:
 a difference between the latest CSI content and a first value is greater than or equal to a second threshold, and the first value is determined based on CSI contents of previous consecutive cycles;   a difference between two most recent consecutive CSI contents is greater than or equal to a third threshold;   a location area identifier currently received by the terminal is different from a location area identifier previously received by the terminal;   hybrid automatic repeat request (HARQ) fails a plurality of times in one cycle; or   a variation of a moving speed of the terminal is greater than or equal to a fourth threshold.   
     
     
         7 . The method according to  claim 1 , wherein the method further comprises:
 reporting, by the terminal, the predicted CSI content and/or third information to a network-side device, wherein the third information is used for assisting the terminal in CSI prediction by the network-side device.   
     
     
         8 . The method according to  claim 7 , wherein the third information indicates the network-side device to stop sending a CSI-RS;
 wherein the third information comprises one or more of the following:   fourth information, wherein the fourth information is used to indicate a time for reporting the predicted CSI content by the terminal;   fifth information, wherein the fifth information indicates an offset time for sending a CSI-RS by the network-side device; or   sixth information, wherein the sixth information indicates an offset time for reporting CSI content by the terminal.   
     
     
         9 . The method according to  claim 7 , wherein the third information indicates the network-side device to send a CSI-RS based on a preconfigured time;
 wherein the third information comprises one or more of the following:   seventh information, wherein the seventh information is used to indicate expiration of a time for reporting the predicted CSI content by the terminal; or   eighth information, wherein the eighth information indicates that the time for reporting the predicted CSI content by the terminal is less than one CSI measurement reporting time.   
     
     
         10 . The method according to  claim 7 , wherein before the reporting, by the terminal, the predicted CSI content to a network-side device, the method further comprises:
 starting, by the terminal, a timer; and   if the timer expires, stopping, by the terminal, CSI prediction and continuing to perform CSI measurement; otherwise, continuing, by the terminal, to perform CSI prediction;   wherein the timer indicates a time for continuously reporting the predicted CSI content by the terminal, or the timer indicates a validity time of the CSI prediction model.   
     
     
         11 . The method according to  claim 7 , wherein before the reporting, by the terminal, the predicted CSI content to a network-side device, the method further comprises:
 starting, by the terminal, a counter; and   if the counter exceeds a fifth threshold, stopping, by the terminal, CSI prediction and continuing to perform CSI measurement; otherwise, continuing, by the terminal, to perform CSI prediction;   wherein the counter indicates a maximum number of cycles for reporting the predicted CSI content supported by the terminal, or the counter indicates the maximum number of times for reporting the predicted CSI content by the terminal.   
     
     
         12 . The method according to  claim 2 , wherein a prediction granularity of the CSI prediction model comprises any one of the following:
 CSI of one time unit;   CSI at a retransmission time;   CSIs of all time units within one CSI measurement reporting cycle; or   CSIs of all time units within each CSI measurement reporting cycle;   or,   wherein a granularity for reporting the predicted CSI content comprises any one of the following:   one CSI content predicted by the CSI prediction model;   batch reporting of CSI contents within a plurality of time units or cycles predicted by the CSI prediction model; or   reporting of all CSI contents within a plurality of time units or cycles predicted by the CSI prediction model.   
     
     
         13 . A CSI prediction method, comprising:
 sending, by a network-side device, first information, wherein the first information is used to indicate a terminal to perform CSI prediction.   
     
     
         14 . The method according to  claim 13 , wherein the sending, by a network-side device, first information comprises:
 receiving, by the network-side device, second information through a first resource, wherein the second information is used to indicate that the terminal meets the triggering condition of CSI prediction; and   in a case that the network-side device detects an energy on the first resource being greater than or equal to a first threshold, sending, by the network-side device, the first information.   
     
     
         15 . The method according to  claim 13 , wherein the triggering condition for CSI prediction comprises one or more of the following:
 a difference between the latest CSI content and a first value is greater than or equal to a second threshold, wherein the first value is determined based on CSI contents of consecutive cycles;   a difference between two most recent consecutive CSI contents is greater than or equal to a third threshold;   a location area identifier currently received by the terminal is different from a location area identifier previously received by the terminal;   HARQ fails a plurality of times in one cycle; or   a variation of a moving speed of the terminal is greater than or equal to a fourth threshold.   
     
     
         16 . The method according to  claim 13 , wherein the method further comprises:
 receiving, by the network-side device, predicted CSI content and/or third information reported by the terminal, wherein the third information is used for assisting the terminal in CSI prediction by the network-side device.   
     
     
         17 . A communication device, comprising a processor, a memory, and a program or an instruction stored in the memory and capable of running on the processor, wherein the program or the instruction, when executed by the processor, causes the communication device to perform:
 in a case that meeting a triggering condition for CSI prediction and receiving first information, performing CSI prediction to obtain predicted CSI content, wherein the first information is used to indicate the communication device to perform CSI prediction.   
     
     
         18 . The communication device according to  claim 17 , wherein when performing CSI prediction to obtain predicted CSI content, the program or the instruction, when executed by the processor, causes the communication device to perform:
 activating a CSI prediction model according to the first information, and performing CSI prediction through the activated CSI prediction model to obtain the predicted CSI content; wherein   input information of the CSI prediction model comprises CSI acquired from a historical measurement on a CSI-RS resource obtained by the communication device.   
     
     
         19 . The communication device according to  claim 18 , wherein when activating a CSI prediction model according to the first information, and performing CSI prediction through the activated CSI prediction model to obtain the predicted CSI content, the program or the instruction, when executed by the processor, causes the communication device to perform:
 obtaining a to-be-activated CSI prediction model and a sample threshold for the CSI prediction model according to the first information;   activating a corresponding CSI prediction model; and   in a case that an amount of CSI measurement data of the communication device is greater than or equal to the sample threshold for the CSI prediction model, performing CSI prediction through the activated CSI prediction model to obtain the predicted CSI content;   or,   obtaining a to-be-activated CSI prediction model according to the first information;   activating a corresponding CSI prediction model; and   in a case that an amount of CSI measurement data of the communication device is greater than or equal to the sample threshold for the CSI prediction model, performing CSI prediction through the activated CSI prediction model to obtain the predicted CSI content.   
     
     
         20 . A communication device, comprising a processor, a memory, and a program or an instruction stored in the memory and capable of running on the processor, wherein when the program or the instruction is executed by the processor, the steps of the method according to  claim 15  are implemented.